© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 45311
    Prev
    Next
    INDEX
    Explanations

    Go build tags

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     where
    -1.59
     może
    -1.42
     when
    -1.38
    )
    -1.35
     選手
    -1.25
     sababu
    -1.25
    .\\
    -1.23
     habían
    -1.22
    :
    -1.21
    .
    -1.20
    POSITIVE LOGITS
    Плюсы
    1.71
    Different
    1.45
    There
    1.32
     encargada
    1.31
    Each
    1.30
    That
    1.30
    
    1.29
    Then
    1.27
    They
    1.27
    Other
    1.27
    Activations Density 0.013%

    No Known Activations